AI/ ai · ai-agents · benchmarks · research

AI Research Agents Still Lose to a Dumb Statistical Baseline

A new benchmark finds AI research agents lose to a simple moving average on overall accuracy, though one model narrowly beats it at reacting to fresh evidence.

AI agents built to predict research trends are getting outperformed by a basic moving average.

Researchers introduced Research Attention Prediction (RAP), a benchmark covering 278 AI/ML fields across 1,390 episodes. At each test point, an LLM agent searches a time-restricted slice of arXiv and predicts how paper shares across eight frozen research directions will shift over the next six months. The study separates two different measures: compositional accuracy, which scores the full predicted distribution, and future-specific updating, which isolates how well a model reacts to genuinely new information once historical activity is already known. On compositional accuracy, all four models tested performed worse than a simple exponentially weighted moving average (EWMA) baseline, even though enabling web search generally helped each model. On future-specific updating, only GPT-5.5 with search re-enabled slightly beat that same EWMA baseline.

The gap matters because it undercuts a common assumption about AI research agents: that search access plus a language model should beat dumb statistical extrapolation. Instead, the paper traces part of the failure to a design choice: models that carry forward a running state do better than models asked to forecast directly from scratch, partly because forecast-first approaches pull in less recent evidence during their searches.

There is a silver lining for anyone building these systems: fine-tuning Qwen3-4B on real outcomes lifted its forecast Spearman correlation by 0.105 on held-out fields it had not seen during training. Grand claims about AI-run research pipelines should probably wait for that kind of tuning to become standard, not the exception.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →